Expert role · Protocol Design

The synopsis, drafted from the evidence you already have.

Objectives, endpoints, design and population — written out of the design, cohort and verdict analyses rather than out of the last protocol you happened to have on file. Every claim carries its source. A clinical scientist reviews it and signs it.

citeciteHUMAN SIGN-OFF

A drafted synopsis, routed to a human signature.

The job · the medical writer or clinical scientist who would otherwise start from a template

You are writing the synopsis anyway. This is the first draft.

Most synopses start life as the last one, with the indication swapped out. That is how a design inherits an endpoint that stopped being defensible three trials ago, and how eligibility criteria accumulate until the cohort you need no longer exists. The work of writing it properly is not the prose — it is going back to the comparable trials, the indication norm and the eligibility arithmetic, and holding the design against them.

That is the part the Protocol Design workspace does first. It reads the study's own feasibility analyses and drafts the synopsis section by section, with the reasoning attached: this endpoint, because these comparable trials; this population, because the cohort sizing says the narrower one will not enrol. You edit it, argue with it, and sign it — or send it back.

What it covers

  • Author the protocol synopsis — objectives, endpoints, design, population
  • Ground each section in the study's feasibility analyses and comparable trials
  • Refine the synopsis as the assessment or amendment-risk signals move
  • Hand the approved synopsis to the downstream statistical and start-up work

In the role registry
Protocol synopsis authoring, grounded in the feasibility assessment

What it drafts

Deliverables — drafts, until signed.

Each artefact arrives with its citations attached and its status explicit. Nothing below is final until a named human signs it.

Protocol synopsis

An eleven-section synopsis drafted from the feasibility assessment — objectives, endpoints, study design, and population — with each section traceable to the analyses it was built from.

Signed off by
a clinical scientist or medical writer

Design & eligibility rationale

The argument behind the design: why this endpoint, this comparator, this randomisation, and these inclusion and exclusion criteria — anchored in the design, cohort and verdict analyses rather than asserted.

Signed off by
a clinical scientist

Comparable-trial evidence pack

The prior trials the design is being measured against, pulled from the registry corpus with their outcomes and, where the record supports it, why the comparable ones stopped.

Signed off by
a clinical scientist

Re-draft on new evidence

When the underlying assessment moves — a new registry entry, a changed cohort estimate — the synopsis can be re-drafted against the current evidence, and anything already signed on the old version is flagged for re-review.

Signed off by
the original signer, again

What it reads

It drafts from the assessment, not from memory

The role has no private knowledge. Every claim it writes traces to an analysis in one of the six pillars, and through that to a public source record.

Design

The synopsis has to justify its design choices against what the indication normally does and against the trials that already tried this.

Competitive landscapeWhy comparable trials failedDesign vs. indication normStatistical powerRegulatory-precedent timelineProtocol-amendment risk

Cohort

Eligibility criteria are where a protocol quietly becomes unenrollable. The draft is written against the cohort that actually exists.

Cohort sizingEligibility complexityReal-world cohort

Verdict

The synopsis has to be consistent with the recommendation the assessment reached — including the risks that qualify it.

Go / No-Go recommendationProbability of successVerdict interpretation
The six pillars in full

How it is governed

A role drafts. A human signs.

This is the part that matters, so it is stated without hedging: the role has no authority to approve anything, and its output has no standing until a qualified person puts their name on it.

  1. The role drafts.

    It produces a draft deliverable with its citations attached. A draft has no standing: it is not approved, not final, and not actionable. The role has no authority to change it into any of those things.

  2. A named human reviews.

    The draft lands as a task for a specific person on your team. They can edit it, reject it, or send it back for a re-draft against the current evidence. Nothing moves until someone with a name has read it.

  3. Sign-off is a Part 11 electronic signature.

    Approval is recorded as a 21 CFR Part 11 electronic signature — attributable to an authenticated identity, time-stamped, and bound to the exact version of the record that was signed.

  4. The whole chain is hash-chained.

    Every draft, edit, review and signature is appended to a tamper-evident, hash-chained audit trail. It is reproducible and exportable, so your QA team can reconstruct who approved what, on what evidence, and when.

  5. Stale approvals are flagged.

    If the underlying evidence later changes, the signed decision is automatically flagged for re-review. Nothing stays approved on data that has since moved.

This role does not replace a qualified clinical scientist or medical writer.

It is a drafting assistant working under human review. It is not an autonomous agent, it does not make regulatory decisions, and its drafts carry no regulatory standing of their own — the signature does.

See a verdict you can actually check.

Send us a protocol — or just a molecule and an indication. We'll return a fully cited feasibility assessment you can trace, line by line, back to public data — yours to defend in a bid, take to your board or investment committee, or hand to a regulator.